Hugging Face's logo

CharlesLi
/
llama_2_cot_simplest_code_math_3_full

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
CharlesLi commited on
Commit
d6f7f16
·
verified ·
1 Parent(s): ebfd4cc

Model save

Browse files
Files changed (9) hide show
  1. README.md +1 -6
  2. all_results.json +3 -3
  3. config.json +1 -1
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. runs/Jan20_12-55-03_dgx-a100-16/events.out.tfevents.1737374128.dgx-a100-16.3029212.0 +3 -0
  8. train_results.json +3 -3
  9. training_args.bin +1 -1
README.md CHANGED
@@ -3,12 +3,9 @@ library_name: transformers
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
6
- - alignment-handbook
7
- - trl
8
- - sft
9
- - generated_from_trainer
10
  - trl
11
  - sft
 
12
  - generated_from_trainer
13
  datasets:
14
  - generator
@@ -23,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
23
  # llama_2_cot_simplest_code_math_3_full
24
 
25
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
26
- It achieves the following results on the evaluation set:
27
- - Loss: 0.5139
28
 
29
  ## Model description
30
 
 
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  datasets:
11
  - generator
 
20
  # llama_2_cot_simplest_code_math_3_full
21
 
22
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
 
 
23
 
24
  ## Model description
25
 
all_results.json CHANGED
@@ -6,9 +6,9 @@
6
  "eval_samples_per_second": 4.303,
7
  "eval_steps_per_second": 1.434,
8
  "total_flos": 2564900782080.0,
9
- "train_loss": 0.7415758800506592,
10
- "train_runtime": 136.7082,
11
  "train_samples": 3980,
12
- "train_samples_per_second": 5.845,
13
  "train_steps_per_second": 0.183
14
  }
 
6
  "eval_samples_per_second": 4.303,
7
  "eval_steps_per_second": 1.434,
8
  "total_flos": 2564900782080.0,
9
+ "train_loss": 0.7377912425994873,
10
+ "train_runtime": 136.5597,
11
  "train_samples": 3980,
12
+ "train_samples_per_second": 5.851,
13
  "train_steps_per_second": 0.183
14
  }
config.json CHANGED
@@ -24,6 +24,6 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.2",
27
- "use_cache": true,
28
  "vocab_size": 32000
29
  }
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.2",
27
+ "use_cache": false,
28
  "vocab_size": 32000
29
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f7c7073cb84c97ac98f47745cd004904d785135698e0b8c4e1cc1598041d71
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86bfdfd10c586a7ed27b9ea54ad4bf5217c5feb2769e728d14c8a366695936f
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9db5553263848bbcab387a0e72a6fc08d51b88c9261a4fd4375d7512a58fa76a
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fe09d4b00ea06bf28a08459fb6f61c6fb1cc7b89fcabebb68df48e8e9d85b2
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c87518d8bcebe8ff6a6ea81debdabf049048fa4746f3c7583b3663e331810552
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361a61b415a9ee1992637383d6c519ca5a754573ca687bdabb07db595bca38e1
3
  size 3590488816
runs/Jan20_12-55-03_dgx-a100-16/events.out.tfevents.1737374128.dgx-a100-16.3029212.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0033ca72068173bd34c549f537e1d8f41e09447c72a65aeeb4dfb2cd7dba7e
3
+ size 6252
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 2564900782080.0,
4
- "train_loss": 0.7415758800506592,
5
- "train_runtime": 136.7082,
6
  "train_samples": 3980,
7
- "train_samples_per_second": 5.845,
8
  "train_steps_per_second": 0.183
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 2564900782080.0,
4
+ "train_loss": 0.7377912425994873,
5
+ "train_runtime": 136.5597,
6
  "train_samples": 3980,
7
+ "train_samples_per_second": 5.851,
8
  "train_steps_per_second": 0.183
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f05db8b9a669f348e9e3ba357659890d64d70af323f4cd55e9b00dd9151033dc
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e99c55ea8357eebdddd4491417d3409bf64bd8354625ced8bb36568489439f
3
  size 7032